© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 170103
    Prev
    Next
    INDEX
    Explanations

    represents a, apply civil

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    標
    0.43
    isms
    0.42
     angle
    0.41
     topics
    0.40
     rendre
    0.40
    ⲟ
    0.40
     Degrees
    0.39
    тный
    0.38
     addBook
    0.38
    N
    0.38
    POSITIVE LOGITS
     Tomlin
    0.46
     jár
    0.45
    autoarima
    0.45
    special
    0.45
    érance
    0.45
     Bezir
    0.44
    sweet
    0.44
     déco
    0.44
    linson
    0.44
     صغير
    0.44
    Activations Density 0.003%

    No Known Activations